Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentences expressing comparisons or contrasts in evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.75
    RectangleBorder
    -0.75
    IntoConstraints
    -0.75
     myſelf
    -0.73
     يتيمه
    -0.73
    ंदीखरीदारी
    -0.70
     AllAfrica
    -0.69
     CreateTagHelper
    -0.67
     auffi
    -0.66
     Италијани
    -0.64
    POSITIVE LOGITS
     quietly
    0.55
    IntegerField
    0.51
     focusing
    0.48
     niche
    0.47
     valuing
    0.47
     small
    0.46
    地味
    0.45
    WebVitals
    0.45
     Quiet
    0.44
     quiet
    0.44
    Act Density 0.263%

    No Known Activations